You close your laptop, come back an hour later, and Claude Code has made 200 tool calls. Which files did it touch? What commands did it run? Did it read your .env?

There’s no built-in way to answer these questions. Claude Code doesn’t keep a structured log of what it did.

session-log fixes that. It’s a PostToolUse hook that appends one JSON line per tool call to a daily log file.

What it captures

Each entry is one line of JSON:

{"ts":"2026-03-07T22:15:00Z","session":"abc123","tool":"Read","detail":"/src/main.rs","cwd":"/project"}
{"ts":"2026-03-07T22:15:01Z","session":"abc123","tool":"Bash","detail":"cargo test","cwd":"/project"}
{"ts":"2026-03-07T22:15:05Z","session":"abc123","tool":"Write","detail":"/src/lib.rs","cwd":"/project"}

Fields: timestamp, session ID, tool name, key parameter (file path or command), and working directory.

Install

curl -fsSL https://raw.githubusercontent.com/Bande-a-Bonnot/Boucle-framework/main/tools/session-log/install.sh | bash

After installation, every tool call gets logged to ~/.claude/session-logs/YYYY-MM-DD.jsonl.

Useful queries

Count tool calls by type:

cat ~/.claude/session-logs/*.jsonl | python3 -c "
import sys, json
from collections import Counter
tools = Counter(json.loads(l)['tool'] for l in sys.stdin)
for tool, count in tools.most_common():
    print(f'  {tool}: {count}')
"

Check if Claude read sensitive files:

grep -E '"detail":".*\.(env|pem|key|secret)' ~/.claude/session-logs/*.jsonl

When this matters

Autonomous agents. If you run Claude Code on a schedule, you need an audit trail. session-log tells you what happened at 3am.

Debugging. Something broke after a Claude session. Trace every file it modified and every command it ran.

Cost awareness. 200 tool calls per session might mean your task is too vague. The logs make it visible.

session-log is part of the Boucle hooks collection, alongside read-once (token savings), file-guard (file protection), git-safe (git safety), and bash-guard (command safety). Each installs independently with a one-liner.

The implementation is 37 lines of Python with 37 tests.